Beyond Line-of-Sight: Cooperative Localization Using Vision and V2X Communication

2025-07-28

AI Summary

In complex urban environments, severe GNSS signal occlusion severely degrades positioning reliability for connected and autonomous vehicles (CAVs). To address this, we propose a decentralized cooperative localization method fusing monocular vision and V2X communication. Leveraging onboard monocular cameras, relative bearing measurements, and V2X-enabled inter-vehicle and infrastructure-to-vehicle communication, our approach establishes a distributed observation framework among CAVs and static environmental beacon nodes—without requiring global perception or GNSS assistance. We theoretically prove that the estimation error converges exponentially within local neighborhoods. The method is validated on a 1:10-scale real-world vehicular network testbed and large-scale simulations, demonstrating effectiveness, scalability, and robustness. Notably, it significantly improves pose estimation accuracy in non-line-of-sight (NLoS) scenarios. This work establishes a novel paradigm for high-reliability, city-scale localization.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Vision for Robotics & Autonomous Driving
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Accurate and robust localization is critical for the safe operation of Connected and Automated Vehicles (CAVs), especially in complex urban environments where Global Navigation Satellite System (GNSS) signals are unreliable. This paper presents a novel vision-based cooperative localization algorithm that leverages onboard cameras and Vehicle-to-Everything (V2X) communication to enable CAVs to estimate their poses, even in occlusion-heavy scenarios such as busy intersections. In particular, we propose a novel decentralized observer for a group of connected agents that includes landmark agents (static or moving) in the environment with known positions and vehicle agents that need to estimate their poses (both positions and orientations). Assuming that (i) there are at least three landmark agents in the environment, (ii) each vehicle agent can measure its own angular and translational velocities as well as relative bearings to at least three neighboring landmarks or vehicles, and (iii) neighboring vehicles can communicate their pose estimates, each vehicle can estimate its own pose using the proposed decentralized observer. We prove that the origin of the estimation error is locally exponentially stable under the proposed observer, provided that the minimal observability conditions are satisfied. Moreover, we evaluate the proposed approach through experiments with real 1/10th-scale connected vehicles and large-scale simulations, demonstrating its scalability and validating the theoretical guarantees in practical scenarios.

Problem

• Enables CAV localization in GNSS-unreliable urban environments
• Uses vision and V2X for occlusion-resistant pose estimation
• Decentralized observer ensures stable pose estimation with minimal landmarks

Innovation

• Vision-based cooperative localization algorithm
• Decentralized observer for connected agents
• Leverages V2X communication and onboard cameras